DETReg: Unsupervised Pretraining With Region Priors for Object Detection

Amir Bar, Xin Wang, Vadim Kantorov, Colorado J. Reed, Roei Herzig, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 14605-14615

Abstract


Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-supervised method that pretrains the entire object detection network, including the object localization and embedding components. During pretraining, DETReg predicts object localizations to match the localizations from an unsupervised region proposal generator and simultaneously aligns the corresponding feature embeddings with embeddings from a self-supervised image encoder. We implement DETReg using the DETR family of detectors and show that it improves over competitive baselines when finetuned on COCO, PASCAL VOC, and Airbus Ship benchmarks. In low-data regimes, including semi-supervised and few-shot learning settings, DETReg establishes many state-of-the-art results, e.g., on COCO we see a +6.0 AP improvement for 10-shot detection and +3.5 AP improvement when training with only 1% of the labels.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bar_2022_CVPR, author = {Bar, Amir and Wang, Xin and Kantorov, Vadim and Reed, Colorado J. and Herzig, Roei and Chechik, Gal and Rohrbach, Anna and Darrell, Trevor and Globerson, Amir}, title = {DETReg: Unsupervised Pretraining With Region Priors for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {14605-14615} }